检索结果-内蒙古大学图书馆

11th International Conference on Recent Trends in computing, ICRTC 2022

作者： Anand, Akshat Rajeswari, D. Department of Data Science and Business Systems School of Computing College of Engineering and Technology SRM Institute of Science and Technology Tamil Nadu Chennai603203 India

ISBN: (纸本)9789811988240

Communications have a crucial role in times of crisis, particularly in times of emergency. Whenever a region is affected by any disaster, social media sites such as Twitter, etc., are a great way to get information out to those who need it the most. Our paper suggests that in times of crisis, when people are worried about finding the right emergency contacts or are experiencing a transformation in their psychological response, they should manually enter their experience into an app to obtain contact information for the nearest SOS. Alternatively, the proposed application suggests scraping hashtags from around the world with web scraping scripts to retrieve geo-referenced tweets in real time. In order to gather accurate data, Twitter's API or some third-party application can be used in the development of this software. When there is a major crisis, social media user behavior plays a vital role, owing to its efficiency and high reliability with swift data dissemination. Anxiety over finding the right emergency team contact may cause people to lose their cool and become unclear about which authority they should call when an emergency occurs. Eventually, our application bridges the gap between clients in need of help and the approved agency that can really provide that support in different circumstances. In the case of, for example, a lost child or a flooded area, our application helps you get in touch with an organization that can assist you in dealing with the situation. We have used CNN-1-D + LSTM, CNN-1-D + Bi-LSTMs, and CNN-1-D + LSTM + Glove-100-D to get maximum accuracy for the classification model. It is possible to use the prototype solution in a novel way to organize immediate assistance with authorities in comprehensive administration, while integrating Twitter or other social platforms into the application can make it a feasible platform for preventive intervention and catastrophe management. © 2023, The Author(s), under exclusive license to Springer Nature

关键词： Emergency services

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence Models in Power Generation for Energy Consumption Prediction

Artificial Intelligence Models in Power Generation for Energ...

引用

International Conference on Emerging Trends in Networks and Computer Communications (ETNCC)

作者： Lit Yang Tan Charis Shwu Chen Kwan Samuel-Soma M. Ajibade Athirah Mohd Ramly Department of Computing and Information Systems School of Engineering and Technology Sunway University Selangor Malaysia Department of Computing School of Architecture Computing and Engineering University of East London London UK

ISBN: (数字)9798350353266

ISBN: (纸本)9798350353273

The incorporation of artificial intelligence (AI) into power-related applications signifies a new and unexplored domain in machine learning for predicting power generation. This novel method utilizes prediction models, often used in different fields, to predict energy-related patterns, providing a unique and specialized viewpoint. The synergy of academicians, AI experts, and industry professionals in the energy sector has resulted in the creation of customized AI models to optimize operational efficiency. By customizing various AI models to suit the distinct attributes of energy scenarios and datasets, these models are positioned to transform energy management methods. This study examines the utilization of AI models to enhance energy efficiency in power generation in Malaysia. The project seeks to predict future power consumption in various sectors, analyze growth rates, and identify sectors with investment potential by developing a Linear Regression model. In addition, a thorough power plan is developed using the estimated energy usage. A comparative analysis is performed to determine the most appropriate model for this particular scenario, which will improve decision-making in the energy sector. The results of this study present promising opportunities for further investigation. By broadening the study's focus to encompass a broader array of AI models and their assessment of performance, it is possible to gain useful insights for predicting power generation. Furthermore, the integration of real-time data streams and the inclusion of feedback loops in the AI models could improve their ability to adapt and increase their accuracy as time progresses.

关键词： Adaptation models Energy consumption Analytical models Linear regression Artificial neural networks Predictive models Data models Artificial intelligence Power generation Streams

来源：评论

学校读者我要写书评

暂无评论

Three-dimensional CityGML building models in mobile augmented reality: a smartphone-based pose tracking system

引用

International Journal of Digital Earth 2021年第1期14卷 32-51页

作者： Christoph Blut Jörg Blankenbach Geodetic Institute Department of Computing in Civil Engineering and Geo-Information SystemsRWTH Aachen UniversityAachenGermany

Many augmented reality(AR)systems are developed for entertainment,but AR and particularly mobile AR potentially have more application possibilities in other *** example,in civil engineering or city planning,AR could be used in combination with CityGML building models to enhance some typical workflows in planning,execution and operation processes.A concrete example is the geo-referenced on-site visualization of planned buildings or building parts,to simplify planning processes and optimize the communication between the participating *** of the main challenges for the visualization lies in the pose tracking,*** real-time estimation of the translation and rotation of the mobile device to align the virtual objects with *** this paper,we introduce a proof-of-concept fine-grained mobile AR CityGML-based pose tracking system aimed at the mentioned *** system estimates poses by combining 3D CityGML data with information derived from 2D camera images and an inertial measurement unit and is fully self-sufficient and operates without external *** results of our evaluation show that CityGML and low-cost off-the-shelf mobile devices,such as smartphones,already provide performant and accurate mobile pose tracking for AR in civil engineering and city planning.

关键词： Mobile augmented reality pose tracking CityGML 3D city model Android smartphone

来源：评论

学校读者我要写书评

暂无评论

IDS: Robust Network Intrusion Detection via Temporal Contrastive Graph Learning

引用

IEEE Transactions on Information Forensics and Security 2025年 20卷 1475-1486页

作者： Wu, Cong Sun, Jianfei Chen, Jing Alazab, Mamoun Liu, Yang Xiang, Yang Wuhan University School of Cyber Science and Engineering Wuhan430072 China Singapore Management University School of Computing and Information Systems Bras Basah Singapore188065 Singapore Charles Darwin University College of Engineering IT and Environment DarwinNT0810 Australia Nanyang Technological University College of Computing and Data Science Jurong West Singapore639798 Singapore Swinburne University of Technology Department of Digital Research MelbourneVIC3122 Australia

In the era of zero trust security models and next-generation networks (NGN), the primary challenge is that network nodes may be untrusted, even if they have been verified, necessitating continuous validation and scrutiny. Effective intrusion detection systems (IDS) are crucial for continuously monitoring network traffic and identifying potential threats. However, traditional IDS approaches often struggle to keep pace with evolving threats, requiring extensive supervised training on labeled datasets. This limitation leads to high false positive rates, low detection accuracy, and a failure to provide real-time detection, thereby undermining the security of NGNs. This paper proposed the first self-supervised learning-based IDS, designed on temporal contrastive graph neural network (GNN), namely TCG-IDS. It innovatively integrates three contrastive learning strategies: temporal contrasting to capture temporal dependencies, asymmetric contrasting to account for the diverse interactions within network data, and masked contrasting to enhance the learning of node representations by masking parts of the data during training. Performance evaluation was conducted on two publicly available network traffic datasets, NF-CSE-CIC-IDS2018-V2 and NF-UNSW-NB15-V2. TCG-IDS achieved a balanced accuracy of 99.48% and 91.48% on two datasets respectively, significantly outperforming state-of-the-art graph learning models. In multi-class detection, TCG-IDS attained a mean false positive rate of 4.15% and 3.34% on the two datasets respectively. Besides, it exhibits high efficiency with its running time of 0.37s and 0.51s on the two datasets to predict per batch of 100 samples. Results highlight the effectiveness and efficiency of TCG-IDS in accurately detecting various types of network intrusions. This work significantly advances the field of network intrusion detection via self-supervised temporal graph learning, offering a promising solution for future network security systems. © 2005-2012

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Brain Stroke Classification with Neuro-Xception and ELM Integration in Deep Learning 2

Revolutionizing Brain Stroke Classification with Neuro-Xcept...

引用

2nd International Conference on computing and Data Analytics, ICCDA 2024

作者： Jagadeesan, S. Ramalingam, Venkadeshan Abinash, P. Ilayaraja, V. Masood, Jafar Ali Ibrahim Syed Tamil Priya, D. School of Computer Science Engineering and Information Systems Vellore Institute of Technology Vellore India UTAS-Shinas branch Department of Computing and Information Sciences Oman School of Computer Science and Engineering Vellore Institute of Technology Vellore India

ISBN: (纸本)9798331542573

Stroke and related neurological disorders are difficult to classify accurately, hence new computational approaches are needed to enhance diagnosis. In order to transform the categorization of brain strokes, this study presents Neuro-Xception, a novel framework that combines the Xception architecture with Extreme Learning Machines (ELM). The rapid learning speed and enhanced generalisation capability of ELMs are combined with the feature extraction expertise of Xception to create Neuro-Xception. Through training on large neuroimaging datasets, Neuro-Xception learns complex patterns that are essential for differentiating between different types and intensities of stroke. By means of extensive testing on various datasets, Neuro-Xception exhibits notable gains in performance compared to traditional techniques, indicating its potential to revolutionise stroke detection in medical environments. Furthermore, Neuro-Xception's scalability and flexibility are enhanced by the combination of Xception and ELMs, which makes it a viable tool for real-time clinical decision support systems and personalised medicine. This study highlights how merging Xception and ELMs can revolutionise neurological healthcare and this development could lead to more accurate and efficient diagnostic techniques for treating stroke patients. Neuro-Xception offers a potential path for increasing diagnosis accuracy and expediting timely medical intervention. It is a major step forward in the use of artificial intelligence to enhance patient outcomes and advance the profession of stroke care. © 2024 IEEE.

关键词： Personalized medicine

来源：评论

学校读者我要写书评

暂无评论

Offset-free distributed predictive control based on fuzzy logic: Application to a real four-tank plant

引用

IFAC-PapersOnLine 2023年第2期56卷 3247-3252页

作者： M. Francisco E. Masero K. Morales-Rodelo J.M. Maestre P. Vega S. Revollar Department of Computing and Automation University of Salamanca Spain Department of Systems Engineering and Automation University of Seville

This paper proposes an offset-free distributed implementation of a model predictive controller that employs fuzzy negotiation between agents. The scheme is based on model augmentation with additional disturbances to enable zero-offset tracking. Moreover, we code the negotiation criteria as a set of suitable fuzzy rules and consider stability and feasibility guarantees in the controller design for the linearized subsystems. We applied the method to an experimental four-tank plant, showing its effectiveness despite the coupling between subsystems and system-model mismatch.

关键词： Linear multivariable systems Predictive control Fuzzy control systems Process control Control of distributed systems

来源：评论

学校读者我要写书评

暂无评论

Efficient Resource Allocation Algorithm in Uplink OFDM-Based Cognitive Radio Networks

引用

Computers, Materials & Continua 2023年第5期75卷 3045-3064页

作者： Omar Abdulghafoor Musbah Shaat Ibraheem Shayea Ahmad Hamood Abdelzahir Abdelmaboud Ashraf Osman Ibrahim Fadhil Mukhlif Herish Badal Norafida Ithnin Ali Khadim Lwas Electronic&Telecommunications Engineering Department The American University of KurdistanDuhokKurdistan RegionIraq CTTC BarcelonaSpain Faculty of Electrical and Electronics Engineering Istanbul Technical UniversityIstanbulTurkey Department of Information Systems King Khalid UniversityMuhayel AseerSaudi Arabia Faculty of Computing and Informatics University Malaysia SabahKota KinabaluMalaysia Information Assurance and Security Research Group(IASRG) School of ComputingFaculty of EngineeringUniversiti Teknologi MalaysiaJohorMalaysia R&D Ministry of Industry and MineralsBaghdadIraq

The computational complexity of resource allocation processes,in cognitive radio networks(CRNs),is a major issue to be ***,the complicated solution of the optimal algorithm for handling resource allocation in CRNs makes it unsuitable to adopt in real-world applications where both cognitive users,CRs,and primary users,PUs,exist in the identical geographical ***,this work offers a primarily price-based power algorithm to reduce computational complexity in uplink scenarioswhile limiting interference to PUs to allowable ***,this paper,compared to other frameworks proposed in the literature,proposes a two-step approach to reduce the complexity of the proposed mathematical *** the first step,the subcarriers are assigned to the users of the CRN,while the cost function includes a pricing scheme to provide better power control algorithm with improved reliability proposed in the second *** main contribution of this paper is to lessen the complexity of the proposed algorithm and to offer flexibility in controlling the interference produced to the users of the primary networks,which has been achieved by including a pricing function in the proposed cost ***,the performance of the proposed power and subcarrier algorithm is confirmed for orthogonal frequency-division multiplexing(OFDM).Simulation results prove that the performance of the proposed algorithm is better than other algorithms,albeit with a lesser complexity of O(NM)+O(Nlog(N)).

关键词： Cognitive radio resource allocation OFDM pricing

来源：评论

学校读者我要写书评

暂无评论

IoT-Driven Solution for Time-Varying Kinematics: 'Reflected'Trajectory Prediction in Dynamic Grasping Tasks 23

IoT-Driven Solution for Time-Varying Kinematics: 'Reflected'...

引用

8th International Conference on Cloud computing and Internet of Things, CCIOT 2023

作者： Ng, Chung Hou Eu, Kok Seng Yap, Kian Meng Ping, Julian Tan Kok Research Centre for Human-Machine Collaboration Department of Engineering Department of Computing and Information Systems School of Engineering and Technology Sunway University Selangor Bandar Sunway Malaysia Taylors University Selangor Petaling Jaya Malaysia

ISBN: (纸本)9798400708046

Time-varying kinematics is a problem with extreme relevance in an increasingly automated world, with no more than a handful of papers studying it. For any industry nowadays to include automation within their pipeline, there will almost always be a need to have purpose-built robotics with expensive and elaborate infrastructure built around it. The reasoning for this is that any robotic-based automation implemented requires movement commands with pin-point precision to work reliably. The Kinematics of the robot is already a well-studied subject, however kinematics only ever reliably works on static object goals, not on moving object goals. This would pose a problem as any industry seeking to implement robotic automation would have no solution toward moving object goals. Additionally, traditional robotic automation incurs time-cost due to the necessity of static object goals during collection. Stopping the object goal or halting robot movement adds to the time overhead, impacting overall efficiency. To address these limitations, this research explores the integration of the Internet of Things (IoT) to develop a more robust "Reflected"trajectory prediction methodology. By leveraging IoT capabilities, it is possible to enhance the adaptability and responsiveness of robotic systems to dynamic grasping tasks involving moving object goals. The introduction of IoT design principles would also allow for a more robust range of robotics to be able to integrate the proposed system, as the computationally complex tasks might not be able to run well alone on a miniaturized robotic system. © 2023 ACM.

关键词： Kinematics

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of DFT and Quadrature Demodulation Algorithms for Complex Spectrum Measurements 34

Comparative Analysis of DFT and Quadrature Demodulation Algo...

引用

34th International Scientific Symposium Metrology and Metrology Assurance, MMA 2024

作者： Podobuev, Sergey A. Krylovich, Anna A. Evsenkina, Alexandra E. Shatokhin, Alexander A. Serov, Nikolay A. Serov, Andrey N. National Research University 'Moscow Power Engineering Institute' Diagnostic Information Technologies Department Moscow Russia National Research University 'Moscow Power Engeneering Institute' Computing Machines Systems and Networks Department Moscow Russia

ISBN: (纸本)9798350352832

To measure the signal spectrum, algorithms based on the implementation of the discrete Fourier transform and quadrature demodulation take place. All of the approaches under consideration are difficult to implement. In addition, the quadrature demodulation method has the potential to have significantly greater accuracy. The main reason for the occurrence of methodological measurement error in the case of DFT algorithms is the 'spectrum leakage' effect. Estimating this error causes significant difficulties. The work shows that for the case of using a quadrature demodulator with an output filter of the moving average type, the discrete Fourier transform and the quadrature demodulator are mathematically equivalent. Simulation modeling of the most popular DFT implementation algorithms (direct implementation, Goertzel algorithm, DFT as filtering and fast Fourier transform) has been carried out. For the quadrature demodulation method, the influence of the output filter on the resulting error in measuring the amplitude and phase spectra of the signal is considered. The results of simulation and mathematical modeling were compared to confirm the reliability of the results. © 2024 IEEE.

关键词： Discrete Fourier transforms

来源：评论

学校读者我要写书评

暂无评论

Smart Education in Smart Cities: Challenges And Solution 9

Smart Education in Smart Cities: Challenges And Solution

引用

9th IEEE International Smart Cities Conference, ISC2 2023

作者： Badshah, Afzal Nasralla, Moustafa M. Jalal, Ateeqa Farman, Haleem Hamdard University Islamabad Campus Department of Computing Islamabad Pakistan College of Engineering Prince Sultan University Smart Systems Engineering Lab Department of Communications and Engineering Riyadh Saudi Arabia University of Science and Technology Department of Computer Science Bannu Pakistan

ISBN: (纸本)9798350397758

Traditional education faces many challenges. Integrating recent technologies (e.g., Artificial Intelligence (AI), Internet of Things (IoT), 5G, etc) into the education system, known as smart education, offers promising solutions. However, the integration of innovative solutions into the traditional system remains limited. The limitations, revealed during the recent COVID-19 pandemic, have now become imperative. This study addresses problems within the traditional system and proposes innovative solutions like smart pedagogy, assessment, classroom, and administration. It explores the shift to smart education and the associated challenges, including computational and social resistance. Innovative education yields concrete benefits, enhancing learner engagement, motivation, attendance, and learning outcomes. Embracing innovative technologies holds the potential to make education more effective and efficient in meeting the evolving needs of learners. © 2023 IEEE.

关键词： Smart city

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：